通过多智能体协作实现任务自适应的工作流构建，效率提升超一半。
(P)rior(D)yna(F)low: A Priori Dynamic Workflow Construction via Multi-Agent Collaboration
- 基于Q表学习优化决策空间，结合历史经验与实时任务特征动态选人。
- 在4个数据集上平均性能提升4.05%，构建与推理成本降至原有30.68%-48.31%。
- 适合需要高效、灵活工作流的复杂任务求解场景，如智能客服、自动化编程。
近期研究表明，精心设计的大型语言模型（LLMs）协同工作流能显著提升任务解决能力，远超单一模型。尽管越来越多研究聚焦于自主工作流构建，但现有方法大多仅依赖历史经验，导致效率与适应性受限。本文提出一种先验动态工作流构建框架，通过Q表学习优化决策空间，指导智能体决策，有效利用历史经验；同时，各智能体评估当前任务进展，前瞻性决定下一执行智能体，使系统能主动为每项任务选择更优结构。此外，引入冷启动初始化、早停和剪枝机制进一步提升效率。在四个基准数据集上的实验表明，本方法可行性与有效性显著，相比顶尖基线平均提升4.05%，工作流构建与推理成本仅为现有方法的30.68%–48.31%。
原文摘要 · Abstract (English)
Recent studies have shown that carefully designed workflows coordinating large language models(LLMs) significantly enhance task-solving capabilities compared to using a single model. While an increasing number of works focus on autonomous workflow construction, most existing approaches rely solely on historical experience, leading to limitations in efficiency and adaptability. We argue that while historical experience is valuable, workflow construction should also flexibly respond to the unique characteristics of each task. To this end, we propose an a priori dynamic framework for automated workflow construction. Our framework first leverages Q-table learning to optimize the decision space, guiding agent decisions and enabling effective use of historical experience. At the same time, agents evaluate the current task progress and make a priori decisions regarding the next executing agent, allowing the system to proactively select the more suitable workflow structure for each given task. Additionally, we incorporate mechanisms such as cold-start initialization, early stopping, and pruning to further improve system efficiency. Experimental evaluations on four benchmark datasets demonstrate the feasibility and effectiveness of our approach. Compared to state-of-the-art baselines, our method achieves an average improvement of 4.05%, while reducing workflow construction and inference costs to only 30.68%-48.31% of those required by existing methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。